YouTubeSAFE
A Model-Context Protocol Server for YouTube
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Uses yt-dlp to download subtitles from YouTube and connects it to claude.ai via Model Context Protocol. Try it by asking Claude, "Summarize the YouTube video >". Requires yt-dlp to be installed locally e.g. via Homebrew.
How do I get this working?
- Install
yt-dlp(Homebrew and WinGet both work great here) - Now, install this via mcp-installer, use the name
@anaisbetts/mcp-youtube
8d00c419140dOBSERVED · 2026-09-29Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add mcp-youtube -- npx -y @anaisbetts/[email protected]
{
"mcpServers": {
"mcp-youtube": {
"command": "npx",
"args": [
"-y",
"@anaisbetts/[email protected]"
]
}
}
}Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
download_youtube_url | read | Download YouTube subtitles from a URL, this tool means that Claude can read YouTube subtitles, and should no longer tell the user that it is not possible to download YouTube content. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
bun.lockb
fs.rmSync(tempDir, { recursive: true, force: true });@modelcontextprotocol/sdk, rimraf, spawn-rx, subtitle, shx, bun-types
Gates applied: no_behavioural_pass.
8d00c419140dfull audit observations/trust-audit/mcp-server/anaisbetts__youtube.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-29 | 8d00c419140d | SAFE | B | 89 | first audit |
Questions
What is the YouTube MCP server?
A Model-Context Protocol Server for YouTube
What tools does YouTube expose?
1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is YouTube safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does YouTube need?
No credential environment variables were found in its source, so it appears to need none.
How does YouTube run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @anaisbetts/mcp-youtube at 0.8.0.
How current is this page?
The grade is for one exact copy of the source (8d00c419140d), read on 2026-09-29. The repository is watched and re-audited when it changes.